Deep Learning & Machine Learning Quiz

What is the primary difference between deep learning and traditional machine learning?

• Deep learning requires labeled data, while traditional ML uses unlabeled data.

• Deep learning automatically extracts features, while traditional ML needs human-engineered features.

• Deep learning models are simpler than traditional ML models.

• Traditional ML uses neural networks, while deep learning does not.

Which of the following is a key characteristic of structured data?

• It has no predefined format.

• It is easy to analyze using deep learning models.

• It is organized into rows and columns, often stored in relational databases.

• It requires feature extraction for analysis.

Which machine learning algorithm is typically used with unlabeled data?

• Support Vector Machine (SVM)

• K-Means Clustering

• Linear Regression

• Random Forest

What is ReLU (Rectified Linear Unit)?

• A type of neural network architecture.

• A function that outputs the input value if positive, and zero if negative.

• A method for optimizing weights in a neural network.

• A type of activation function for convolutional layers.

Which type of neural network is primarily used for image recognition tasks?

• Recurrent Neural Network (RNN)

• Convolutional Neural Network (CNN)

• Long Short-Term Memory (LSTM)

• Transformer Network

What is the purpose of backpropagation in a neural network?

• To split the data into training and testing sets.

• To initialize the weights of the neural network.

• To adjust the weights of the neural network based on error calculations.

• To calculate the output of the neural network.

Which of the following is an example of semi-structured data?

• A CSV file containing customer records.

• A JSON file containing information about a customer's name, age, and purchases.

• A raw text file containing blog posts.

• A relational database containing employee information.

Which of the following is labeled data used for supervised learning?

• A collection of images without annotations.

• A dataset containing movie reviews with sentiment labels ('positive' or 'negative').

• A set of customer data with no labels.

• A time series dataset without target values.

What is the main goal of unsupervised learning?

• To predict a specific label or outcome for each data point.

• To learn patterns and relationships in data without labels.

• To train a model using large amounts of labeled data.

• To perform regression tasks.

What is an advantage of using deep learning over traditional machine learning?

• It is always faster to train.

• It requires less data to achieve good performance.

• It can automatically extract complex features without human intervention.

• It works well with only small datasets.